llm-shell 0.9.2 → 0.10.0

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/scanner.rb

@@ -0,0 +1,337 @@
+# encoding: utf-8
+
+module CodeRay
+  module Scanners
+    
+    # = Scanner
+    #
+    # The base class for all Scanners.
+    #
+    # It is a subclass of Ruby's great +StringScanner+, which
+    # makes it easy to access the scanning methods inside.
+    #
+    # It is also +Enumerable+, so you can use it like an Array of
+    # Tokens:
+    #
+    #   require 'coderay'
+    #   
+    #   c_scanner = CodeRay::Scanners[:c].new "if (*p == '{') nest++;"
+    #   
+    #   for text, kind in c_scanner
+    #     puts text if kind == :operator
+    #   end
+    #   
+    #   # prints: (*==)++;
+    #
+    # OK, this is a very simple example :)
+    # You can also use +map+, +any?+, +find+ and even +sort_by+,
+    # if you want.
+    class Scanner < StringScanner
+      
+      extend Plugin
+      plugin_host Scanners
+      
+      # Raised if a Scanner fails while scanning
+      ScanError = Class.new StandardError
+      
+      # The default options for all scanner classes.
+      #
+      # Define @default_options for subclasses.
+      DEFAULT_OPTIONS = { }
+      
+      KINDS_NOT_LOC = [:comment, :doctype, :docstring]
+      
+      attr_accessor :state
+      
+      class << self
+        
+        # Normalizes the given code into a string with UNIX newlines, in the
+        # scanner's internal encoding, with invalid and undefined charachters
+        # replaced by placeholders. Always returns a new object.
+        def normalize code
+          # original = code
+          code = code.to_s unless code.is_a? ::String
+          return code if code.empty?
+          
+          if code.respond_to? :encoding
+            code = encode_with_encoding code, self.encoding
+          else
+            code = to_unix code
+          end
+          # code = code.dup if code.eql? original
+          code
+        end
+        
+        # The typical filename suffix for this scanner's language.
+        def file_extension extension = lang
+          @file_extension ||= extension.to_s
+        end
+        
+        # The encoding used internally by this scanner.
+        def encoding name = 'UTF-8'
+          @encoding ||= defined?(Encoding.find) && Encoding.find(name)
+        end
+        
+        # The lang of this Scanner class, which is equal to its Plugin ID.
+        def lang
+          @plugin_id
+        end
+        
+      protected
+        
+        def encode_with_encoding code, target_encoding
+          if code.encoding == target_encoding
+            if code.valid_encoding?
+              return to_unix(code)
+            else
+              source_encoding = guess_encoding code
+            end
+          else
+            source_encoding = code.encoding
+          end
+          # print "encode_with_encoding from #{source_encoding} to #{target_encoding}"
+          code.encode target_encoding, source_encoding, :universal_newline => true, :undef => :replace, :invalid => :replace
+        end
+        
+        def to_unix code
+          code.index(?\r) ? code.gsub(/\r\n?/, "\n") : code
+        end
+        
+        def guess_encoding s
+          #:nocov:
+          IO.popen("file -b --mime -", "w+") do |file|
+            file.write s[0, 1024]
+            file.close_write
+            begin
+              Encoding.find file.gets[/charset=([-\w]+)/, 1]
+            rescue ArgumentError
+              Encoding::BINARY
+            end
+          end
+          #:nocov:
+        end
+        
+      end
+      
+      # Create a new Scanner.
+      #
+      # * +code+ is the input String and is handled by the superclass
+      #   StringScanner.
+      # * +options+ is a Hash with Symbols as keys.
+      #   It is merged with the default options of the class (you can
+      #   overwrite default options here.)
+      #
+      # Else, a Tokens object is used.
+      def initialize code = '', options = {}
+        if self.class == Scanner
+          raise NotImplementedError, "I am only the basic Scanner class. I can't scan anything. :( Use my subclasses."
+        end
+        
+        @options = self.class::DEFAULT_OPTIONS.merge options
+        
+        super self.class.normalize(code)
+        
+        @tokens = options[:tokens] || Tokens.new
+        @tokens.scanner = self if @tokens.respond_to? :scanner=
+        
+        setup
+      end
+      
+      # Sets back the scanner. Subclasses should redefine the reset_instance
+      # method instead of this one.
+      def reset
+        super
+        reset_instance
+      end
+      
+      # Set a new string to be scanned.
+      def string= code
+        code = self.class.normalize(code)
+        super code
+        reset_instance
+      end
+      
+      # the Plugin ID for this scanner
+      def lang
+        self.class.lang
+      end
+      
+      # the default file extension for this scanner
+      def file_extension
+        self.class.file_extension
+      end
+      
+      # Scan the code and returns all tokens in a Tokens object.
+      def tokenize source = nil, options = {}
+        options = @options.merge(options)
+        
+        set_tokens_from_options options
+        set_string_from_source source
+        
+        begin
+          scan_tokens @tokens, options
+        rescue => e
+          message = "Error in %s#scan_tokens, initial state was: %p" % [self.class, defined?(state) && state]
+          raise_inspect e.message, @tokens, message, 30, e.backtrace
+        end
+        
+        @cached_tokens = @tokens
+        if source.is_a? Array
+          @tokens.split_into_parts(*source.map { |part| part.size })
+        else
+          @tokens
+        end
+      end
+      
+      # Cache the result of tokenize.
+      def tokens
+        @cached_tokens ||= tokenize
+      end
+      
+      # Traverse the tokens.
+      def each &block
+        tokens.each(&block)
+      end
+      include Enumerable
+      
+      # The current line position of the scanner, starting with 1.
+      # See also: #column.
+      #
+      # Beware, this is implemented inefficiently. It should be used
+      # for debugging only.
+      def line pos = self.pos
+        return 1 if pos <= 0
+        binary_string[0...pos].count("\n") + 1
+      end
+      
+      # The current column position of the scanner, starting with 1.
+      # See also: #line.
+      def column pos = self.pos
+        return 1 if pos <= 0
+        pos - (binary_string.rindex(?\n, pos - 1) || -1)
+      end
+      
+      # The string in binary encoding.
+      # 
+      # To be used with #pos, which is the index of the byte the scanner
+      # will scan next.
+      def binary_string
+        @binary_string ||=
+          if string.respond_to?(:bytesize) && string.bytesize != string.size
+            #:nocov:
+            string.dup.force_encoding('binary')
+            #:nocov:
+          else
+            string
+          end
+      end
+      
+    protected
+      
+      # Can be implemented by subclasses to do some initialization
+      # that has to be done once per instance.
+      #
+      # Use reset for initialization that has to be done once per
+      # scan.
+      def setup  # :doc:
+      end
+      
+      def set_string_from_source source
+        case source
+        when Array
+          self.string = self.class.normalize(source.join)
+        when nil
+          reset
+        else
+          self.string = self.class.normalize(source)
+        end
+      end
+      
+      def set_tokens_from_options options
+        @tokens = options[:tokens] || @tokens || Tokens.new
+        @tokens.scanner = self if @tokens.respond_to? :scanner=
+      end
+      
+      # This is the central method, and commonly the only one a
+      # subclass implements.
+      #
+      # Subclasses must implement this method; it must return +tokens+
+      # and must only use Tokens#<< for storing scanned tokens!
+      def scan_tokens tokens, options  # :doc:
+        raise NotImplementedError, "#{self.class}#scan_tokens not implemented."
+      end
+      
+      # Resets the scanner.
+      def reset_instance
+        @tokens.clear if @tokens.respond_to?(:clear) && !@options[:keep_tokens]
+        @cached_tokens = nil
+        @binary_string = nil if defined? @binary_string
+      end
+      
+      SCAN_ERROR_MESSAGE = <<-MESSAGE
+
+
+***ERROR in %s: %s (after %s tokens)
+
+tokens:
+%s
+
+%s
+
+surrounding code:
+%p  ~~  %p
+
+
+***ERROR***
+
+      MESSAGE
+      
+      def raise_inspect_arguments message, tokens, state, ambit
+        return File.basename(caller[0]),
+          message,
+          tokens_size(tokens),
+          tokens_last(tokens, 10).map(&:inspect).join("\n"),
+          scanner_state_info(state),
+          binary_string[pos - ambit, ambit],
+          binary_string[pos, ambit]
+      end
+      
+      SCANNER_STATE_INFO = <<-INFO
+current line: %d  column: %d  pos: %d
+matched: %p  state: %p
+bol?: %p,  eos?: %p
+      INFO
+      
+      def scanner_state_info state
+        SCANNER_STATE_INFO % [
+          line, column, pos,
+          matched, state || 'No state given!',
+          bol?, eos?,
+        ]
+      end
+      
+      # Scanner error with additional status information
+      def raise_inspect message, tokens, state = self.state, ambit = 30, backtrace = caller
+        raise ScanError, SCAN_ERROR_MESSAGE % raise_inspect_arguments(message, tokens, state, ambit), backtrace
+      end
+      
+      def tokens_size tokens
+        tokens.size if tokens.respond_to?(:size)
+      end
+      
+      def tokens_last tokens, n
+        tokens.respond_to?(:last) ? tokens.last(n) : []
+      end
+      
+      # Shorthand for scan_until(/\z/).
+      # This method also avoids a JRuby 1.9 mode bug.
+      def scan_rest
+        rest = self.rest
+        terminate
+        rest
+      end
+      
+    end
+    
+  end
+end

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/sql.rb

@@ -0,0 +1,169 @@
+module CodeRay
+module Scanners
+  
+  # by Josh Goebel
+  class SQL < Scanner
+    
+    register_for :sql
+    
+    KEYWORDS = %w(
+      all and any as before begin between by case check collate
+      each else end exists
+      for foreign from full group having if in inner is join
+      like not of on or order outer over references
+      then to union using values when where
+      left right distinct
+    )
+    
+    OBJECTS = %w(
+      database databases table tables column columns fields index constraint
+      constraints transaction function procedure row key view trigger
+    )
+    
+    COMMANDS = %w(
+      add alter comment create delete drop grant insert into select update set
+      show prompt begin commit rollback replace truncate
+    )
+    
+    PREDEFINED_TYPES = %w(
+      char varchar varchar2 enum binary text tinytext mediumtext
+      longtext blob tinyblob mediumblob longblob timestamp
+      date time datetime year double decimal float int
+      integer tinyint mediumint bigint smallint unsigned bit numeric
+      bool boolean hex bin oct
+    )
+    
+    PREDEFINED_FUNCTIONS = %w( sum cast substring abs pi count min max avg now )
+    
+    DIRECTIVES = %w( 
+      auto_increment unique default charset initially deferred
+      deferrable cascade immediate read write asc desc after
+      primary foreign return engine
+    )
+    
+    PREDEFINED_CONSTANTS = %w( null true false )
+    
+    IDENT_KIND = WordList::CaseIgnoring.new(:ident).
+      add(KEYWORDS, :keyword).
+      add(OBJECTS, :type).
+      add(COMMANDS, :class).
+      add(PREDEFINED_TYPES, :predefined_type).
+      add(PREDEFINED_CONSTANTS, :predefined_constant).
+      add(PREDEFINED_FUNCTIONS, :predefined).
+      add(DIRECTIVES, :directive)
+    
+    ESCAPE = / [rbfntv\n\\\/'"] | x[a-fA-F0-9]{1,2} | [0-7]{1,3} | . /mx
+    UNICODE_ESCAPE =  / u[a-fA-F0-9]{4} | U[a-fA-F0-9]{8} /x
+    
+    STRING_PREFIXES = /[xnb]|_\w+/i
+    
+    STRING_CONTENT_PATTERN = {
+      '"' => / (?: [^\\"] | "" )+ /x,
+      "'" => / (?: [^\\'] | '' )+ /x,
+      '`' => / (?: [^\\`] | `` )+ /x,
+    }
+    
+    def scan_tokens encoder, options
+      
+      state = :initial
+      string_type = nil
+      string_content = ''
+      name_expected = false
+      
+      until eos?
+        
+        if state == :initial
+          
+          if match = scan(/ \s+ | \\\n /x)
+            encoder.text_token match, :space
+          
+          elsif match = scan(/(?:--\s?|#).*/)
+            encoder.text_token match, :comment
+            
+          elsif match = scan(%r( /\* (!)? (?: .*? \*/ | .* ) )mx)
+            encoder.text_token match, self[1] ? :directive : :comment
+            
+          elsif match = scan(/ [*\/=<>:;,!&^|()\[\]{}~%] | [-+\.](?!\d) /x)
+            name_expected = true if match == '.' && check(/[A-Za-z_]/)
+            encoder.text_token match, :operator
+            
+          elsif match = scan(/(#{STRING_PREFIXES})?([`"'])/o)
+            prefix = self[1]
+            string_type = self[2]
+            encoder.begin_group :string
+            encoder.text_token prefix, :modifier if prefix
+            match = string_type
+            state = :string
+            encoder.text_token match, :delimiter
+            
+          elsif match = scan(/ @? [A-Za-z_][A-Za-z_0-9\$]* /x)
+            encoder.text_token match, name_expected ? :ident : (match[0] == ?@ ? :variable : IDENT_KIND[match])
+            name_expected = false
+            
+          elsif match = scan(/0[xX][0-9A-Fa-f]+/)
+            encoder.text_token match, :hex
+            
+          elsif match = scan(/0[0-7]+(?![89.eEfF])/)
+            encoder.text_token match, :octal
+            
+          elsif match = scan(/[-+]?(?>\d+)(?![.eEfF])/)
+            encoder.text_token match, :integer
+            
+          elsif match = scan(/[-+]?(?:\d[fF]|\d*\.\d+(?:[eE][+-]?\d+)?|\d+[eE][+-]?\d+)/)
+            encoder.text_token match, :float
+          
+          elsif match = scan(/\\N/)
+            encoder.text_token match, :predefined_constant
+            
+          else
+            encoder.text_token getch, :error
+            
+          end
+          
+        elsif state == :string
+          if match = scan(STRING_CONTENT_PATTERN[string_type])
+            encoder.text_token match, :content
+          elsif match = scan(/["'`]/)
+            if string_type == match
+              if peek(1) == string_type  # doubling means escape
+                encoder.text_token match + getch, :content
+              else
+                encoder.text_token match, :delimiter
+                encoder.end_group :string
+                state = :initial
+                string_type = nil
+              end
+            else
+              encoder.text_token match, :content
+            end
+          elsif match = scan(/ \\ (?: #{ESCAPE} | #{UNICODE_ESCAPE} ) /mox)
+            encoder.text_token match, :char
+          elsif match = scan(/ \\ . /mox)
+            encoder.text_token match, :content
+          elsif match = scan(/ \\ | $ /x)
+            encoder.text_token match, :error unless match.empty?
+            encoder.end_group :string
+            state = :initial
+          else
+            raise "else case \" reached; %p not handled." % peek(1), encoder
+          end
+          
+        else
+          raise 'else-case reached', encoder
+          
+        end
+        
+      end
+      
+      if state == :string
+        encoder.end_group state
+      end
+      
+      encoder
+      
+    end
+    
+  end
+  
+end
+end

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/taskpaper.rb

@@ -0,0 +1,36 @@
+module CodeRay
+module Scanners
+  
+  class Taskpaper < Scanner
+    
+    register_for :taskpaper
+    file_extension 'taskpaper'
+    
+  protected
+    
+    def scan_tokens encoder, options
+      until eos?
+        if match = scan(/\S.*:.*$/)                  # project
+          encoder.text_token(match, :namespace)
+        elsif match = scan(/-.+@done.*/)             # completed task
+          encoder.text_token(match, :done)
+        elsif match = scan(/-(?:[^@\n]+|@(?!due))*/) # task
+          encoder.text_token(match, :plain)
+        elsif match = scan(/@due.*/)                 # comment
+          encoder.text_token(match, :important)
+        elsif match = scan(/.+/)                     # comment
+          encoder.text_token(match, :comment)
+        elsif match = scan(/\s+/)                    # space
+          encoder.text_token(match, :space)
+        else                                         # other
+          encoder.text_token getch, :error
+        end
+      end
+      
+      encoder
+    end
+    
+  end
+  
+end
+end

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/text.rb

@@ -0,0 +1,26 @@
+module CodeRay
+  module Scanners
+    
+    # Scanner for plain text.
+    # 
+    # Yields just one token of the kind :plain.
+    # 
+    # Alias: +plaintext+, +plain+
+    class Text < Scanner
+      
+      register_for :text
+      title 'Plain text'
+      
+      KINDS_NOT_LOC = [:plain]  # :nodoc:
+      
+    protected
+      
+      def scan_tokens encoder, options
+        encoder.text_token string, :plain
+        encoder
+      end
+      
+    end
+    
+  end
+end

data/lib/llm/shell/internal/coderay/lib/coderay/scanners/xml.rb

@@ -0,0 +1,17 @@
+module CodeRay
+module Scanners
+
+  load :html
+
+  # Scanner for XML.
+  #
+  # Currently this is the same scanner as Scanners::HTML.
+  class XML < HTML
+
+    register_for :xml
+    file_extension 'xml'
+    
+  end
+
+end
+end